Flash system having multiple fingerprint tables

Abstract

A system and method for managing tables in a storage system is described.

What is claimed is: 
     
       1. A storage system comprising:
 a storage device; 
 a plurality of fingerprint tables comprising one or more entries corresponding to data stored in the storage device, the one or more entries having a corresponding probability of the data being deduplicated and wherein the one or more entries are added to a particular fingerprint table of the plurality of fingerprint tables that stores entries having a range of probabilities that the corresponding probability falls within; and 
 a storage controller communicatively coupled to the storage device, the storage controller configured to:
 determine that an event has occurred; and 
 modify one of the plurality of fingerprint tables. 
 
 
     
     
       2. The storage system of  claim 1 , wherein the plurality of fingerprint
 tables comprises: 
 a first table comprising a first set of entries corresponding to data stored in the storage device which have likelihoods of deduplication that is greater than or equal to a threshold probability; and 
 a second table comprising a second set of entries corresponding to data stored in the storage device which have likelihoods of deduplication that is less than the threshold probability. 
 
     
     
       3. The storage system of  claim 1 , wherein the storage controller is further
 configured to: 
 maintain attributes corresponding to usage of data objects storage in the storage device; and 
 read the attributes corresponding to the objects, responsive to detecting the event. 
 
     
     
       4. The storage system as recited in  claim 3 , wherein the attributes comprise one or more of: access, data age, device performance, device heath, error correction use data, deduplication rate, read shift voltage, frequency of update, and an error rate. 
     
     
       5. The storage system of  claim 1 , wherein the event comprises one of: a garbage collection operation, a health binning operation, a block calibration operation, a device access operation and a wear levelling operation. 
     
     
       6. The storage system of  claim 1 , wherein the storage controller is further configured to:
 perform a data access to a fingerprint data of one of the plurality of fingerprint tables as part of a deduplication operation. 
 
     
     
       7. The storage system of  claim 1 , wherein the data includes patterns. 
     
     
       8. The storage system of  claim 1 , wherein the storage system is a flash system. 
     
     
       9. The storage system of  claim 1 , wherein the one or more entries comprise hashes. 
     
     
       10. A method comprising:
 determining that an event has occurred; and 
 modifying one of a plurality of fingerprint tables comprising one or more entries corresponding to data stored in a storage device, the one or more entries having a corresponding probability of the data being deduplicated and wherein the one or more entries are added to a particular fingerprint table of the plurality of fingerprint tables that stories entries having a range of probabilities that the corresponding probability falls within. 
 
     
     
       11. The method of  claim 10 , wherein the plurality of fingerprint tables
 comprises: 
 a first table comprising a first set of entries corresponding to data stored in the storage device which have likelihoods of deduplication that is greater than or equal to a threshold probability; and 
 a second table comprising a second set of entries corresponding to data stored in the storage device which have likelihoods of deduplication that is less than the threshold probability. 
 
     
     
       12. The method of  claim 10 , further comprising:
 maintaining attributes corresponding to usage of data objects storage in the storage device; and 
 reading the attributes corresponding to the objects, responsive to detecting the event. 
 
     
     
       13. The method as recited in  claim 12 , wherein the attributes comprise one or more of: access, data age, device performance, device heath, error correction use data, deduplication rate, read shift voltage, frequency of update, and an error rate. 
     
     
       14. The method of  claim 10 , wherein the event comprises one of: a garbage collection operation, a health binning operation, a block calibration operation, a device access operation and a wear levelling operation. 
     
     
       15. The method of  claim 10 , further comprising:
 performing a data access to a fingerprint data of one of the plurality of fingerprint tables as part of a deduplication operation. 
 
     
     
       16. The method of  claim 10 , wherein the data includes patterns. 
     
     
       17. The method of  claim 10 , wherein the storage device is a flash storage device. 
     
     
       18. The method of  claim 10 , wherein the one or more entries comprise hashes. 
     
     
       19. A non-transitory, computer-readable medium comprising instructions which, when executed by a processing device of a storage system, cause the processing device to:
 determine that an event has occurred; and 
 modify one of a plurality of fingerprint tables comprising one or more entries corresponding to data stored in a storage device, the one or more entries having a corresponding probability of the data being deduplicated and wherein the one or more entries are added to a particular fingerprint table of the plurality of fingerprint tables that stories entries having a range of probabilities that the corresponding probability falls within. 
 
     
     
       20. The non-transitory, computer readable storage medium of  claim 19 , wherein the plurality of fingerprint tables comprises:
 a first table comprising a first set of entries corresponding to data stored in the storage device which have likelihoods of deduplication that is greater than or equal to a threshold probability; and 
 a second table comprising a second set of entries corresponding to data stored in the storage device which have likelihoods of deduplication that is less than the threshold probability.